Facial expression recognition has emerged as a critical research area in health monitoring, enabling healthcare professionals to assess patients' emotional and psychological states for timely intervention and personalized care. However, existing methods often struggle to balance computational accuracy with energy efficiency. To address this challenge, this paper proposes FE-SpikeFormer - a high-accuracy, low-energy, and deployment-friendly Spiking Neural Network (SNN) for facial emotion recognition. The proposed architecture comprises three key components: the initial convolution module, the spiking extraction block, and the spiking integration block. These three modules collectively support detailed and contextual feature extraction, promote spatial feature integration, and strengthen the representational capacity of spiking signals. Meanwhile, a joint verification is conducted in both controlled laboratory settings and real-world hospital scenarios. Experimental results demonstrate that FE-SpikeFormer achieves top-three recognition accuracy among state-of-the-art methods, while utilizing only 6.93 million parameters. Moreover, it exhibits strong robustness against various noise conditions, underscoring its potential for practical deployment in healthcare environments.

Human activity recognition has played a crucial role in healthcare information systems due to the fast adoption of artificial intelligence (AI) and the internet of thing (IoT). Most of the existing methods are still limited by computational energy, transmission latency, and computing speed. To address these challenges, we develop an efficient human activity recognition in-memory computing architecture for healthcare monitoring. Specifically, a mechanism-oriented model of Ag/a-Carbon/Ag memristor is designed, serving as the core circuit component of the proposed in-memory computing system. Then, one-transistor-two-memristor (1T2M) crossbar array is proposed to perform high-efficiency multiply-accumulate (MAC) operation and high-density memory in the proposed scheme. To facilitate understanding of the proposed efficient human activity recognition in-memory computing design, self-attention ConvLSTM module, multi-head convolutional attention module, and recognition module are proposed. Furthermore, the proposed system is applied to perform human activity recognition, which contains eleven different human activities, including five different postural falls, and six basic daily activities. The experimental results show that the proposed system has advantages in recognition performance (≥ 0.20% accuracy, ≥ 1.10% F1-score) and time consumption (approximately 8∼10 times speed up) compared to existing methods, indicating an advancement in smart healthcare applications.

One of the most promising flexible sources in decarbonized power systems is based on electric vehicles fleets equipped with V2G technology, which can exchange bidirectional power flows with the grid matching the system operator request, and providing valuable ancillary services, as far as frequency and voltage regulation are concerned. Providing these services requires deploying resilient, highly scalable, plug-and-play, and privacy-preserving computing frameworks for charging/discharging orchestration according to the requested active and reactive power profiles at the point of connections. For this purpose, this paper proposes a decentralized and self-organizing scheme based on a Peer-to-Peer architecture, leveraging privacy-preserving through cooperative consensus protocols. The effectiveness of the proposed scheme is demonstrated by both theoretical and experimental studies, which have been obtained on a hardware testbed simulating a variable number of grid-connected vehicles under realistic operation scenarios.

The authors hope that this overview and suggestions will stimulate and contribute to further ongoing discussions and interesting research work and industrial applications in some fields of Systems, Man and Cybernetics.

Negative emotion (e.g., anger, fear) may influence normal driver behavior, resulting in serious traffic accidents. Thus, developing an automatic driver emotion classification method is necessary and urgent. Most of the existing methods are performed in realistic indoor environment and always lack effective utilization of heterogeneous information, resulting in low accuracy and reliability. In this paper, a novel dual-pathway driver emotion classification network using multi-task learning strategy is proposed. To illustrate the design of the proposed driver emotion classification network, three modules are constructed: 1) visual-facial data processing module; 2) driving behavioral data processing module; 3) fusion output module. Meanwhile, considering the influence of emotional states on driving behavior, a comprehensive analysis is conducted to distinguish the positive, neutral, and negative influence on driving behavior. Furthermore, a joint verification in both realistic indoor environment (i.e., laboratory simulation on the PPB-Emo dataset) and real-world outdoor scenario is performed. The experimental results illustrate that the proposed network exhibits superior performance in terms of classification accuracy and response time, achieving good balance between classification accuracy and running speed in internet of things scenarios.

With the rapid adoption of Internet of Things (IoT) and artificial intelligence (AI), lithium-ion battery state-of-health (SOH) estimation plays an important role in guaranteeing the secure and stable functioning of various domains. However, the majority of the existing methods are constrained by factors, such as transmission latency, computational energy, and computing speed. To address these challenges, we develop a time-frequency hybrid neuromorphic computing architecture for battery SOH estimation. Specifically, an eco-friendly, biodegradable memristor crossbar array is designed, enabling high-energy efficiency and high-performance density in the proposed system. To improve the understanding of the designed time-frequency hybrid neuromorphic computing system, a local information extraction module, a time-frequency feature fusion module, and a global information perception module are proposed. Furthermore, the proposed system is validated on two publicly available battery ageing data sets (i.e., the CALCE-CS2 data set and the National Aeronautics and Space Administration data set). The experimental results show that the system exhibits superior performance to that of the state-of-the-art (SOTA) methods in terms of estimation accuracy (highest estimation accuracy), time consumption (approximately 8–12 times faster), and transmission latency (approximately 10 times faster). This study is expected to promote the advancement and evolution of next-generation computing systems, enabling the realization of low-power consumption and high-density information processing in IoT scenarios.

Traffic sign detection is of great significance to the development of the Intelligent Transportation System (ITS) as a database for environmental awareness. The main challenges of existing traffic sign detection method are inaccurate small object detection, difficult mobile deployment, and complex working environment. Based on these, a vehicle-mounted adaptive traffic sign detector (VATSD) for small-sized signs in multiple working conditions is proposed in this paper. First, the Backbone of the detector is optimized. A feature tight fusion structure is designed to constitute a new feature extraction module, DCSP, which improves the feature extraction capability and the detection accuracy of small objects with negligible additional parameters. Second, an image enhancement network IENet with an adaptive joint filtering strategy is proposed. The IENet enables the dynamic selection of filters and thus adaptively optimizes low-quality images under multiple conditions to improve the accuracy of subsequent detection tasks. The proposed method has experimented on three traffic sign datasets and the detection accuracy increased by up to 7.6% compared to the original. The proposed detector demonstrates superiority over other state-of-the-art (SOTA) methods in terms of small object detection accuracy, detection speed, and environmental adaptability. Further, we deployed VATSD to Jetson Xavier NX and achieved a detection speed of 21.6 FPS, meeting real-time requirements.

The combination of the Metaverse and intelligent transportation systems (ITS) holds significant developmental promise, especially for visual perception tasks. However, the acquisition of high-quality scene data poses a challenging and expensive endeavor. Meanwhile, the visual disparity between the Metaverse and the physical world poses an impact on the practical applicability of the visual perception tasks. In this paper, a Metaverse Intelligent Traffic Visual Framework, MITVF, is developed to guide the implementation of visual perception tasks in the physical world. Firstly, a two-stage metadata optimization strategy is proposed that can efficiently provide diverse and high-quality scene data for traffic perception models. Specifically, an element reconfigurability strategy is proposed to flexibly combine dynamic and static traffic elements to enrich the data with a low cost. A diffusion model-based metadata optimization acceleration strategy is proposed to achieve efficient improvement of image resolution. Secondly, a Meta-Physical adaptive learning method is proposed, and further applied to visual perception tasks to compensate for the visual disparity between the Metaverse and the physical world. Experimental results show that MITVF achieves a 10$\times$acceleration in optimization speed, ensuring the image quality and reconstructing diverse. Further, MITVF is applied to the traffic object detection task to verify the effectiveness and validity. The performance of the model trained with 5k real data exceeded that of the model trained with 200k real data, with AP$_{50}$reaching 67.7%.

Despite neuromorphic computing (NC) technologies offer tremendous potential in executing computationally intensive tasks with high efficiency and low latency, most of existing methods are still difficult to achieve software-comparable accuracy. To address this challenge, we develop a multimodal local–global NC system (MLG-NCS) that can capture local characteristics and exchange global cross-modal information sufficiently. Specifically, a high-density memristor crossbar array is prepared to perform efficient parallel in-memory operations, serving as the fundamental component of the proposed MLG-NCS. To facilitate understanding of the proposed MLG-NCS design, the local feature representation module, the global cross-modal interaction module, and the output module are designed. The experimental results show that the proposed system has advantages in classification accuracy (ranked top three), time consumption (approximately ten times speed up), and latency (about 1.2–15.3 times faster), enabling good inter-related tradeoffs between latency, efficiency, and accuracy. This study is expected to promote the revolution and development of next-generation computing system, which takes a firm step toward artificial general intelligence (AGI).

Video sentiment analysis can effectively establish the relationship between the emotion state and the multimodal information, while still suffer from intensive computation and low efficiency, due to the von Neumann computing architecture. Here, we present a brain-inspired hierarchical interactive in-memory computing (IMC) system, which can efficiently solve ‘von Neumann bottleneck’, enabling cross-modal interactions and semantic gap elimination. First, a 1T1M synapse array is fabricated using cost-effective, highly stable, flexible, and eco-friendly carbon materials, offering efficient analog multiply-accumulate operations. To illustrate the complexity of the proposed brain-inspired hierarchical interactive IMC system, three modules are proposed: 1) unimodal extraction module, 2) hierarchical interactive module, 3) output module. Furthermore, the proposed system is validated by applying it to video sentiment analysis. The experimental results demonstrate that the proposed system outperforms the existing state-of-the-art methods with high computational efficiency and good robustness. This work opens up a new way to achieve the deep integration of nanomaterials, deep learning, and modern electronics into IMC.

The precise location of insulators in infrared images is of great significance for insulator condition monitoring and fault diagnosis. Due to the characteristics of insulators themselves and the use of handheld infrared cameras, insulators usually appear in infrared images with different aspect ratios and main axis orientations. Therefore, it is very important and necessary to make full use of the prior knowledge of the insulator itself to accurately locate it. However, most of the existing methods use axial horizontal detection boxes to detect insulators, which cannot take into account the characteristics of the insulator well. When there are large overlapping areas of two horizontal detection boxes, the nonmaximum suppression algorithm may lead to missed detection of the object. To further improve the accuracy of the detection algorithm, this article makes full use of the prior features carried by the insulator itself, and optimizes faster region-based convolutional neural networks (R-CNN) from five aspects: rectangular box representation, feature extraction, candidate box generation, anchor design, and feature alignment. An oriented detection model for infrared images of insulators is constructed. Comparative experiments with a variety of mainstream detection methods were carried out on the constructed infrared dataset. The results show that the proposed method is superior to other models in detection accuracy. When the intersection and union ratio is 0.5, the average precision reaches 95.08%. In addition, it can also effectively predict the shape and angle information of insulators in complex scenes, laying a beneficial foundation for subsequent diagnosis automation tasks.

To achieve net-zero emissions economy, the transition to online entertainment and retail, aging populations, urban population growth, and pressures on public finance have created huge interests for human to run cities differently and smartly. A term titled smart city is created which is considered as an idealistic city, where the quality of life for citizens is greatly improved by utilizing information and communication technology (ICT), new services, and new city infrastructures to efficiently achieve the value, such as sustainable and resilient development. The eco-sustainable method has to be used in several aspects, such as energy, mobility, environment, and social services. Research and development in smart cities is expanding exponentially. SMC is one of the core sponsors of the IEEE Smart Cities.

Moisture is one of the critical factors to determine the service life of transformers. The moisture inside the transformer oil-immersed insulation could be quantified with feature parameters. This article proposes and develops a genetic algorithm support vector machine (GA-SVM) model to carry out the moisture diagnosis. Present findings reveal that these feature parameters can be obtained by using frequency-domain spectroscopy. Therefore, a novel model for predicting the frequency-domain spectroscopy curves is first reported based on a small number of samples, which could be utilized to obtain the feature parameters database to develop GA-SVM. Then, the moisture diagnosis in the lab and field conditions is presented to verify its feasibility and accuracy. The novelty of this article is in an exploration of the reported model as an intelligent based moisture diagnosis tool for power transformers.

The multimicrogrids (MMGs) system of the island group is geographically dispersed with different ownership. In this article, a control strategy based on distributed model predictive control is proposed to optimize the economic scheduling of MMGs on an island group. The strategy is designed based on the dynamic noncooperative game theory to regulate the trading behavior among microgrids (MGs) belonging to different owners. The mechanism maximizes the economic benefits of the MGs under the premise of ensuring the closed-loop stability of the single MG system. Only a minimum amount of communication information exchange is needed, which avoids the demands of the central controller and can help the MG to protect its privacy of operating information. The proposed strategy can maximize the benefits of power trading and significantly reduce the operating cost of the system while ensuring the balance between supply and demand. Simulation results are presented to prove the fairness and validity of the proposed control strategy.

Power and energy systems are lifeline infrastructures to civilization. Their stable operation and security of supply are essential for the daily life of the people. Typically, they are characterized by a central generation infrastructure using large-scale power plants. The electricity is transported via long-distance transmission lines on high-voltage levels and distributed via distribution grids to customers on medium and low-voltage levels.

Driven by the global need for decarbonization, low carbon power generators are currently being deployed at a rapid rate. Subsequently, the power grid is posed with high operational risks due to intermittent power generation and uncertain energy demand. Along with demand-side management, energy storage plays a critical role in balancing energy supply with demand. The techno-economic analysis is conducted to compare different technological options to meet an energy problem (e.g., grid support and off-grid energy supply). Several techno-economic analyses have been conducted for low carbon energy technologies; however, different approaches were used and it is difficult to compare the present works of literature. This paper describes the on-going work of IEEE P2814, a current standards project developing recommended practices on techno-economic metrics for hybrid energy and storage systems. This standards project defines techno-economic terminologies used in the development, construction, and operation of renewable energy and electrical energy storage systems. Here, a preliminary techno-economic framework is presented and discussed. Some key aspects that need to be considered in the techno-economic analysis include the timescale of analysis and quantifying carbon emission contribution of the technologies. Future work for the standards project will be described.

For microgrids (MGs) optimal operation, one heated topic is the uncertainty management associated with renewable variations and electricity load forecasting errors. On the other hand, the networking of MGs is receiving an increasing attention in recent years. In this paper, an interactive energy management strategy is developed for high renewable-penetrated MGs. The control method includes two steps. In the first step, a local optimization is proposed for each microgrid to minimize the operation cost during the whole scheduling periods. In the second step, a global optimization is conducted for networked microgrids. CVaR based risk averse measure is introduced here to provide a risk-hedging strategy for microgrids energy management. Formulated models are solved by the easily implemented and computationally inexpensive mix integer linear programming (MILP) solver. Case studies demonstrate the feasibility of the proposed method by identifying optimal scheduling results.

In data streaming environments such as a smart grid, it is impossible to restrict each data chunk to have the same number of samples in each class. Hence, in addition to the concept drift, classification problems in streaming data environments are inherently imbalanced. However, streaming imbalanced and concept drifting problems in the power system and smart grid have rarely been studied. Incremental learning aims to learn the correct classification for the future unseen samples from the given streaming data. In this paper, we propose a new incremental ensemble learning method to handle both concept drift and class imbalance issues. The class imbalance issue is tackled by an imbalance-reversed bagging method that improves the true positive rate while maintains a low false positive rate. The adaptation to concept drift is achieved by a dynamic cost-sensitive weighting scheme for component classifiers according to their classification performances and stochastic sensitivities. The proposed method is applied to a case study for the electricity pricing in Australia to predict whether the price of New South Wales will be higher or lower than that of Victorias in a 24-h period. Experimental results show the effectiveness of the proposed algorithm with statistical significance in comparison to the state-of-the-art incremental learning methods.

Current methods for nonintrusive load monitoring (NILM) problems assume that the number of appliances in the target location is known, however, this may not be realistic. In real-world situations, the initial setup of the site can be known but new appliances may be added by users after a period of time, especially in a household or nonrestrictive scenarios. In this sense, current methods without detecting new appliances may not accurately monitor loads of different appliances and scenarios. In this paper, a novel new appliance detection method is proposed for NILM with imbalance classification for appliances switching ON or OFF. The prediction of appliances being switched ON or OFF is an important step in load monitoring and the switching on frequencies for coffee machine and air conditioning in a household are different, making the problem inherently imbalanced. Experimental results show that the proposed method yields outstanding performance against the well-known oversampling method, synthetic minority oversampling technique, on real NILM applications in scenarios with new appliances emerging.

In Day-ahead Power Market (DAM), Load Serving Entities (LSEs) needs to submit their load schedule to market operator beforehand. For reduction of the total cost, the disparity of the price of DAM and the price of RDM (Real Day Market) should be considered by the LSEs. Therefore, the problem is that a more accurate load-forecasting model sometimes provide a price that has an interspace will lead to a lower cost. Facing this issue, this paper initiates a load forecasting model considering the Costing Correlated Factor (CCF) with deep Long Short-term Memory (LSTM). The target of the forecast model contains both accuracy section and power cost section. At the same time, the construct of LSTM can of fset the sacrificed accuracy. Also, this paper uses an Adaptive Moment Estimation algorithm for network training and the type of neuron is Rectified Linear Unit (ReLU). A numerical study based on practical data is presented and the result shows that LSTM with CCF can reduce energy cost with acceptable accuracy level.

Due to various weather perturbation effects, the stochastic nature of real-life solar irradiance has been a major issue for solar photovoltaic (PV) system planning and performance evaluation. This paper aims to discover clearness index (CI) patterns and to construct centroids for the daily CI profiles. This will be useful in being able to provide a standardized methodology for PV system design and analysis. Four years of solar irradiance data collected from Johannesburg (26.21 S, 28.05 E), South Africa are used for the case study. The variation in CI could be significant in different seasons. In this paper, cluster analysis with Gaussian mixture models (GMM), K-Means with Euclidean distance (ED), K-Means with Manhattan distance, Fuzzy C-Means (FCM) with ED, and FCM with dynamic time warping (FCM DTW) are performed for the four seasons. A case study based on sizing a stand-alone solar PV and storage system with anaerobic digestion biogas power plants is used to examine the usefulness of the clustering results. It concludes that FCM DTW and GMM can determine the correct PV farm rated capacity with an acceptable energy storage capacity, with 36 and 46 rather than 1457 solar irradiance profiles, respectively.

Detecting and identifying High Impedance Fault (HIF) in distribution system is an essential task for a secure and reliable grid. The ability for relaying system to differentiate HIF and heavy load condition is still a challenging problem as their current and voltage characteristics are very similar. This paper demonstrates how discrete wavelet transform can be used to identify the two cases. It also reviews how big data analytics could be used to improve this long standing problem. A simple power system model constructed in DigSILENT Power Factory performs the short circuit analysis for the HIF and the open circuit islanding for the heavy load conditions. MATLAB will be used for discrete wavelet transform analysis for the output from the power system model.

In this paper, the state-of-the-art of big data is reviewed. Challenges, opportunities and tools will be discussed. Some emerging technologies will be looked to promote big data applications. The applications of big data in smart grid in some countries will be summarized too.

Low carbon emission is one of the main targets for smart grid planning. To achieve this goal, intermittent energies such as wind and solar are integrated to the power systems increasingly. However, this may create huge challenges to the power system operators for balancing the generation and demand at all times and guaranteeing the system reliability at the same time. With high penetration of renewable energies, power system operators are compelled to curtail the loads when the power system cannot rely on power from renewable energies continuously due to strong dependence on the environment. As an important defense to protect the power network from collapsing and to keep the system integrating, load shedding has been designed and proposed for decades. However, most of the shedding schemes consider the load increasing instead of lack of generation. This paper applies a load shedding scheme with considering both voltage and frequency changes when the generation is inadequate since the power system cannot obtain the expected renewable generation and renewable energies are highly penetrated into the grid.

With more uncertainty and variability existing in smart grid, deterministic load flow, which is used to analyze the operation conditions on a daily routine and planning the power systems for future investment, could not solve the problems with consideration of renewable generation intermittence and load variation. Nowadays, with more attentions are paid to the environment, carbon emission problem is one of the main concerns in smart grid strategies and planning. It is a great opportunity and challenge for planners to take good care of all stakeholders' interests. Multi-objectives need to be considered when making a critical decision. This paper presents result comparisons between probabilistic optimal load flow and probabilistic load flow by considering both carbon emission and minimization of power loss of the entire grid. The framework is applied to the modified IEEE 14-bus system, which is modeled in Power Factory Dig SILENT, with intermittent wind energy source and load variation consideration.

This paper presents few key issues that must be taken into account for energy system development and planning. Discussions on energy efficiency, renewables deployment and energy policy are required to improve energy security of any countries. Some figures in China will be used to demonstrate the proposed ideas. Some novel strategies and methods will be discussed. An example on demand response will be included.

This paper reports some design and requirements needed for applying smart meters to micro grid. Few practical applications will be used to demonstrate the benefit obtained with this approach. International standard used for communication will be included in the design. Good practice will be proposed.

In this paper, both bottom-up and top-down models for demand response with agent-base approach and neural networks have been investigated. Simulations have been carried out with practical load data from the UK and Canada. Results show that each approach has its advantages and disadvantages depending on difference application scenarios.

In this paper, Decision Support System (DSS) from 30 years ago to the near future will be studied to investigate the development trend of DSS. A typical DSS architecture has been described and the requirement of the DSS functionality implementation is illustrated in this article. Because all of the DSSs are projected-oriented, researchers are focused on developing general architecture to adapt as many cases as possible. Researchers begin to investigate the dynamic interaction and multi-criteria for the DSS application. In the near future, with the development of cloud computing, some cloud-based and agent-based DSSs will be adopted to various applications.

Nowadays, electricity is mainly produced by large central generation plants. However, generators with lower capacities are increasingly used for distributed generation (DG). Distributed generators are applicable for improving supply reliability with considerations of renewable energy, environmental protection, peak load shaving and deferred investments in network expansion. Comparing to central generation, DG technologies are flexible in size, fuel, operation and expandability. Most of DGs are installed at distribution level. Various kinds of loads as well as active compensation devices may be connected in parallel with DG. Moreover, low capacity generation systems are more susceptible to power quality issues. This paper presents challenges of implementation of DG in practical area electric power systems under the impacts from both utility side and demand side.