Multimodal emotion recognition (MER) has been widely adopted in affective computing and human–computer interaction. However, real-world multimodal streams frequently suffer from missing or incomplete modalities due to sensor failures, privacy constraints, and heterogeneous acquisition costs, which often causes severe performance degradation for models trained under complete inputs. To address this issue, we propose hierarchical VAE–diffusion for emotion reconstruction (HVDER), a latent-space generative framework for incomplete MER. HVDER first employs modality-specific variational autoencoders (VAEs) to project language, visual, and audio features into a unified low-dimensional latent space with KL-regularized structure. Then, a two-stage coarse-to-fine conditional diffusion module completes missing modality latents by recovering global emotion semantics followed by refining local discriminative details. Finally, the completed and observed modality representations are fused for emotion prediction, optimized end-to-end with a multiobjective loss integrating reconstruction, diffusion matching, cross-modal alignment, and classification supervision. Extensive experiments on CMU-MOSEI and CMU-MOSI validate the effectiveness and robustness of HVDER. Under fixed modality-missing settings, HVDER achieves average ACC2/F1 of 76.8/75.4 on CMU-MOSEI and 73.4/72.9 on CMU-MOSI, outperforming representative baselines across all modality combinations. Under random missing with a high missing rate of MR = 0.7, HVDER maintains ACC2/F1 of 75.4/72.5 on CMU-MOSEI and 68.0/67.2 on CMU-MOSI, indicating a stronger performance lower bound in severely incomplete scenarios. Ablation studies further confirm that latent-space modeling and the coarse-to-fine diffusion design jointly contribute to the main performance gains.

Concept reduction that preserves binary relations is an emerging reduction theory in the field of Formal Concept Analysis. Its core lies in reducing the number of concepts while ensuring that the original information is not lost, thereby significantly improving the efficiency of data processing. Based on Object Pictorial Diagram (OPD), this paper proposes a novel attribute-oriented concept reduction method that preserves complementary binary relations. First, this paper clarifies the definition of attribute-oriented concept reduction and presents a specific method for addressing it from the perspective of OPD. Against the backdrop of smart education's growing emphasis on data-driven decision-making, accurately diagnosing learners' knowledge states has become a core requirement for instructional reform and personalized tutoring. Practically, by integrating learners' response data to exercises, cognitive diagnosis is conducted by using the obtained attribute-oriented concept reduction results, enabling an in-depth analysis of learners' knowledge states and cognitive structures. Experimental results demonstrate that the proposed method exhibits high efficiency in both solving attribute-oriented concept reduction and performing cognitive diagnosis. The proposed method provides robust support for assessing learners' learning states and enhances the interpretability of various personalized learning applications.

The unmanned aerial vehicle (UAV) resupply mode offers a viable alternative to parcel delivery by replenishing ground vehicles at intermediate open-space supply points. Usually, orders are treated as equally important with no guarantees of on-time delivery. In this paper, we propose a priority-based delivery framework to efficiently manage real-time delivery demands with varying priorities. Specifically, this framework integrates a fleet of UAVs for resupply and trucks for final delivery. By considering the inherent priority of orders and their elapsed waiting time, a dynamic priority discipline is introduced and customized to different order contexts. This approach ensures that urgent orders are prioritized to ensure timely fulfillment within their deadlines, while low-prioritized orders can still be completed without excessive waiting. Simulations using a real-world city map of Helsinki, along with mobility features of both trucks and UAVs, show significant performance gains over baseline schemes in terms of on-time delivery rate, average delivery time, and waiting fairness among all orders.

Global navigation satellite systems (GNSS) error source analysis is crucial for identifying factors that affect the accuracy of positioning, navigation, and timing services (PNT). Detecting and correcting these factors is essential for enhancing overall service accuracy. Traditional methods primarily focus on surface-level receiver output data, which may overlook underlying factors. Additionally, analyzing daily generated data is expensive and requires advanced proficiency. This research uses a novel temporal-spatial analysis approach to analyze GNSS error sources with artificial intelligence (AI) model support. We develop a noise segments dataset categorized into six types, with a particular focus on ionospheric disclosure, a deeper-level receiver data calculating PNT result. By applying clustering combined with a z-score normalization filter (ZFilter), we identify highly consistent noise segments in daily data, which aids in understanding potential causes. We then employ a multi-model deep learning approach to classify the noise segments, as opposed to relying on a single baseline model. Additionally, we experiment with semi-supervised learning through pseudo-labeling to improve classification performance. Our experiments show that our classifier achieves approximately 84% accuracy in identifying the noise segments.

With the development of driverless technology, unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs) have been widely used in the realm of commodity delivery. In the scenario with a high requirement for timeliness commodity delivery, the mobile unmanned retail mode has grabbed tremendous sights. However, the traditional retail mode solely focuses on presetting routes for delivery, but fails to deal with the real-time change of customers orders with the assistance of UAVs and UGVs. In this paper, we propose an air-ground cooperative real-time delivery scheme based on joint scheduling. Specifically, UGVs deliver commodities to customers based on spatial-temporal costs (e.g., delivery distance and order urgency). The UAV serves to replenish UGVs with commodity resources, achieving a balance between regional resource consumption and UAV resource replenishment based on joint scheduling. Finally, experimental results show our scheme outperforms other baseline schemes in terms of customers average waiting time, UGVs average delivery delay time, and UAV total flight distance.

Electric Vehicle (EV) is regarded as the optimal alternative to traditional fuel-powered vehicles. However, the exponential surge in EV charging demand poses challenges in charging infrastructure planning and charging behavior management. The efficacy of traditional Grid-to-Vehicle (G2V) charging mode, which obtains power from the grid, is curtailed by the limited number and uneven distribution of charging facilities, inevitably leading to charging congestion. Instead, the concept of Vehicle-to-Vehicle (V2V) charging has emerged as a spatio-temporally flexible charging mode, which expands EV's role from consumer to provider, forming V2V pairs and utilizing urban Parking Lots (PLs) as charging locations. In this paper, we propose a Hybrid Heterogeneous Modes (HHM)-based EV charging optimization scheme in urban settings. Building upon the G2V mode, we introduce synchronous and asynchronous V2V charging modes as optimization strategies, integrating and exploiting the unique advantages of each mode. We also utilize global EV charging scheduling and comprehensively take four dimensions into consideration (energy trading cost, travel cost, waiting time cost and loss cost), thus achieving flexible mode selection, V2V pairing, and designated charging locations. Simulations confirm the effectiveness of the proposed scheme in reducing total charging costs, optimizing user service experiences, and improving charging facility utilization rates.

Edge caching is a promising technology to reduce backhaul strain and content access delay in Internet of Vehicles (IoV). It precaches frequently used contents close to vehicles through intermediate roadside units. Previous edge caching works often assume that content popularity is known in advance or obeys simplified models. However, such assumptions are unrealistic, as content popularity varies with uncertain spatial-temporal traffic demands in IoVs. Federated learning (FL) enables vehicles to predict popular content with distributed training. It preserves the training data remain local, thereby addressing privacy concerns and communication resource shortages. This article investigates a mobility-aware edge caching strategy by exploiting asynchronous FL and deep reinforcement learning (DRL). We first implement a novel asynchronous FL framework for local updates and global aggregation of stacked autoencoder (SAE) models. Then, utilizing the latent features extracted by the trained SAE model, we adopt a hybrid filtering model for predicting and recommending popular content. Furthermore, we explore intelligent caching decisions after content prediction. Based on the formulated Markov decision process (MDP) problem, we propose a DRL-based solution, and adopt neural network-based parameter approximations for the curse of dimensionality in RL. Extensive simulations are conducted based on real-world data trajectory. Especially, our proposed method outperforms federated averaging, least recently used, and NoDRL, and the edge hit rate is improved by roughly 6%, 21%, and 15%, respectively, when the cache capacity reaches 350 MB.

In recent years, great attention has been paid on Electric Vehicles (EVs) in terms of environmental pollution. Here, EVs can greatly reduce the environmental pollution, compared with traditional Internal Combustion Vehicles (ICVs). However, since EVs cannot be replenished fast like ICVs, the rigid deployment of charging infrastructure and its limited charging capability, leads to service congestion particularly due to a large number of EVs being parked with charging demand. Compared to CSs with rigid extension in location and charging facilitates, the Vehicle-to-Vehicle (V2V) charging service provides a spatial and temporal advance in flexibility, with potential to supplement with G2V charging mode, which can supplement or even replace the G2V Charging Mode. In this paper, we propose a hybrid V2V charging scheme, consisting of direct and asynchronous V2V charging modes, to achieve a great charging flexibility and alleviate the burden for grid load. Here, we estimate the Minimum Waiting Time (MWT) under each mode, as guidance to switch between modes and optimize charging service under each mode. Results show that our proposed hybrid V2V charging scheme outperforms literature works, in terms of average waiting time and number of full charged EVs.

Compared with traditional images, multispectral images (MSIs) contain more spectral bands and higher data dimensions. The existing MSI classification model has high computational complexity and consumes a lot of computing resources. In this letter, we propose a lightweight multispectral classification method named CABNN based on binary neural networks (BNNs) to effectively have a trade-off between model performance and computational cost. First, we modify and binarize the MobileNetV1 network and add almost computation-free shortcuts to enhance the expressive capability. Secondly, since the BNN is sensitive to the distribution of activation functions, we introduce RPReLU with learnable coefficients to automatically adjust activation distribution at almost no extra cost. Lastly, considering that MSIs have multiple channels, we utilize an efficient channel attention (ECA) module to assign different weights to each channel to concentrate on crucial features and suppress insignificant features. We conduct experiments on four public MSI datasets, including NaSC-TG2, EuroSAT, GID Fine land-cover classification, and UC Merced Land Use. Extensive experiments demonstrate that the proposed CABNN has higher efficiency and better comprehensive performance than the state-of-the-art methods across the board.

As a key enabler in the green transport system, the popularity of Electric Vehicles (EV) has attracted attention from academia and industrial communities. However, the driving range of EVs is inevitably affected by the insufficient battery volume, as such EV drivers may experience trip discomfort due to a long battery charging time (under traditional plug-in charging service). One feasible alternative to accelerate the service time to feed electricity is the battery switch technology, by cycling switchable (fully-recharged) batteries at Battery Switch Stations (BSSs) to replace the depleted batteries from incoming EVs. Along with recent advance of vehicle cooperation through emerging Information Communication Technology (ICT), in this paper we propose a Mobile Edge Computing (MEC) driven architecture to gear the intelligent battery switch service management for EVs. Here, the decision making on where to switch battery is operated by EVs in a distributed manner. Besides, the Vehicle-to-Vehicle (V2V) communication in line with public transportation bus system is applied to operate flexible information exchange between EVs and BSSs. Dedicated MEC functions are positioned for bus system to efficiently disseminate BSSs status and aggregate EVs’ reservations, concerning the massive signalling exchange cost. The Global Controller (GC) is positioned as cloud server to gather BSSs (service providers) status and EVs’ reservations (clients), and predict the service availability of BSS (e.g., whether/when a battery can be switched). We conduct performance evaluation to show the advantage of MEC system in terms of reduction of communication cost, and BSS service management scheme regarding reduction of service waiting time (e.g., how long to wait for battery switch) and increase of service satisfaction rate (e.g., how many batteries to switch for EVs).

This article aims to design an intelligent mobile charging control mechanism for electric vehicles (EVs), by promoting charging reservations (including service start time, expected charging time, and charging location). EV mobile charging could be implemented as an alternative recharging solution, wherein charge replenishment is provided by economically mobile plug-in chargers, capable of providing on-site charging services. With intelligent charging management, readily available mobile chargers are predictable and could be efficiently scheduled toward EVs with charging demand, based on updated context collected from across the charging network. The context can include critical information relating to charging sessions and charging demand. Furthermore, with reservations introduced, accurate estimations on charging demand for a future moment are achievable, and correspondingly, optimal mobile chargers selection can be obtained. Therefore, charging demands across the network can be efficiently and effectively satisfied, with the support of intelligent system-level decisions. In order to evaluate critical performance attributes, we further carry out extensive simulation experiments with practical concerns to verify our insights observed from the theoretical analysis. Results show great performance gains by promoting the reservation-based mobile charger selection, especially for mobile chargers equipped with suffice power capacity. Note to Practitioners-The convenience of charging service is one major concern for EVs, especially when an urgent charging is required while none charging points are reachable. Recently, a Chinese EV company (NIO, Inc., Shanghai, China) is promoting its mobile charger (ES8 model) to Tesla. Driven by such market trend, this article proposes an efficient approach toward intelligent scheduling of mobile chargers toward parked EVs. Different from fixed charging stations focusing on the problem of long waiting times, the proposed solution is applicable to charging-on-demand with precharging appointment at mobile chargers. Preliminary experiments show great charging efficiency achieved by concerning the issue of where to reserve, i.e., the consideration of optimal selection on mobile chargers. Such mobile charging services can coexist with the governmental or pilots' initiated charging station deployment. However, future research will need to evaluate the holistic service platform.

The introduction of Electric Vehicles (EVs) leads to new concern on the E-Mobility. Making charging reservation, by considering the EV's arrival time and its expected charging time at Charging Stations (CSs) has been studied to predict the dynamic status of CSs. In this paper, we propose a Mobile Edge computer Geared v2x for E-mobility Ecosystem (MEGEE), as a decentralized alternative to the conventional centralized cloud based architecture. MEGEE enables the Vehicular Delay/Disruption Tolerant Networking (VDTN)-driven anycasting for information delivery, and Mobile Edge Computing (MEC) functioned CSs for information mining and aggregation. MEGEE efficiently and timely processes essential charging reservations and charging control information, through the Internet of EVs and MEC servers. Our studies show that MEGEE can achieve the close charging performance as performed by the centralized system, while offers a significant saving in communications cost.

With the growing popularization of Electric Vehicles (EVs), charging management has become an increasingly important research problem in smart cities. Different from plug-in charging technology, we alternatively enable the battery switch technology to provide fast EV charging (reduce the service waiting time from tens of minutes to a few minutes), by facilitating the switchable (fully-recharged) batteries maintained at CSs and also the batteries cycling procure to refresh their availability. Nevertheless, potential hot spot may still happen at CSs, due to running out of switchable batteries as well as long batteries charging queue. With this concern, we next propose a reservation based EV charging management scheme to alleviate such situation, considering EVs' anticipated charging reservations (including arrival time, expected charging time) to coordinate EVs' charging plans. Results under the Helsinki city scenario with realistic EV and CS characteristics show the advantage of our enabling technology, in terms of minimized waiting time for the battery switch as the benefit of EV drivers, and higher number of batteries switched as the benefit of CSs.

Continuous and effective developments in Autonomous Vehicles (AVs) are happening on daily basis. Industries nowadays, are interested in introducing less costly and highly controllable AVs to public. Current so-called AVP solutions are still limited to a very short range (e.g., even only work at the entrance of car parks). This paper proposes a parking scheduling scheme for long-range AVP (LAVP) case, by considering mobility of Autonomous Vehicles (AVs), fuel consumption and journey time. In LAVP, Car Parks (CPs) are used to accommodate increasing numbers of AVs, and placed outside city center, in order to avoid traffic congestions and ensure road safety in public places. Furthermore, with positioning of reference points to guide user-centric long-term driving and drop-off/pick-up passengers, simulation results under the Helsinki city scenario shows the benefits of LAVP. The advantage of LAVP system is also reflected through both analysis and simulation.

Charging management for Electric Vehicles (EVs) on-the-move (moving on the road with certain trip destinations) is becoming important, concerning the increasing popularity of EVs in urban city. However, the limited battery volume of EV certainly influences its driver's experience. This is mainly because the EV needed for intermediate charging during trip, may experience a long service waiting time at Charging Station (CS). In this paper, we focus on CS-selection decision making to manage EVs' charging plans, aiming to minimize drivers' trip duration through intermediate charging at CSs. The anticipated EVs' charging reservations including their arrival time and expected charging time at CSs, are brought for charging management, in addition to taking the local status of CSs into account. Compared to applying traditionally applying cellular network communication to report EVs' charging reservations, we alternatively study the feasibility of applying Vehicle-to-Vehicle (V2V) communication with Delay/Disruption Tolerant Networking (DTN) nature, due primarily to its flexibility and cost-efficiency in Vehicular Ad hoc NETworks (VANETs). Evaluation results under the realistic Helsinki city scenario show that applying the V2V for reservation reporting is promisingly cost-efficient in terms of communication overhead for reservation making, while achieving a comparable performance in terms of charging waiting time and total trip duration.

In order to resolve the tension between continuously growing mobile users' demands on content access and the scarcity of the bandwidth capacity over backhaul links, we propose in this paper a fully distributed ICN-based caching scheme for content objects in Radio Access Network (RAN) at eNodeBs. Such caching scheme operates in a cooperative way within neighbourhoods, aiming to reduce cache redundancy so as to improve the diversity of content distribution. The caching decision logic at individual eNodeBs allows for adaptive caching, by taking into account dynamic context information, such as content popularity and availability. The efficiency of the proposed distributed caching scheme is evaluated via extensive simulations, which show great performance gains, in terms of a substantial reduction of backhaul content traffic as well as great improvement on the diversity of content distribution, etc.

This paper presents a holistic peer selection scheme in multi-domain environments, aiming to mitigate Peer-to-Peer (P2P) traffic volumes over expensive inter-domain links as well as the maintenance of desirable P2P users' perceived service quality. The mechanism combines the traditional locality-aware peer selection with the consideration of ISP business relationship. By leveraging between the two peering strategies, the risk of possible congestion on critical inter-connected links can be effectively alleviated due to more concentrated P2P traffic over fewer inter-ISP links under pure cooperative peering schemes. According to our analytical modelling, the proposed hybrid approach is able to achieve better performance for P2P users, and can retain desirable network efficiency as of the cooperative peer selection strategy. Our modelling based analysis offers the incentives to perform peer selections in multi-domain environments wherein non-cooperative networks and cooperative networks coexist.