Serverless computing brings another revolution to cloud computing as function-as-a-service (FaaS) where the applications are abstracted as a group of functions. Serverless applications are cost-effective and manage resources efficiently but the lack of performance modeling and energy optimization affects the potential users' broad adoption of serverless computing. Performance enhancement and energy optimization are necessary to guarantee the serverless applications' service level agreement (SLA). This review paper presents various performance metrics in serverless computing, including cost, scalability, latency, energy consumption, resource utilization, fault tolerance, and response time. Based on these metrics, various performance modeling and energy optimization techniques have been explored to reduce energy consumption and improve system efficiency. Furthermore, the review investigates software platforms for implementing serverless computing, including AWS Lambda, Apache OpenWhisk, Azure Functions, and Google Cloud Functions, highlighting key findings and limitations. This comprehensive review serves as a guide for researchers, directing them toward new and promising research directions in the field.

Community structure is a common feature of social networks and many community discovery algorithms have emerged through the study of this feature. The gravitational field model is an effective method to realize community division. However, the current gravitational field model lacks a comprehensive consideration of field properties such as the internal stability of the gravitational field. Therefore, in this paper, we define and quantify the attributes of the gravitational field by taking advantage of the field's strength in describing the joint action of groups. Then, we propose a social network gravitational field community detection model (GF-CDM). GF-CDM selects the field kernel node based on a random walk and then presents an adaptive expansion function of fusion field stability to divide the observable network into overlapping and non-overlapping clusters. The model was evaluated on four real network datasets and five artificial network datasets of different sizes. Experimental results show that our proposed model outperforms the other four benchmark algorithms in modularity, ARI index, and field average stability, which can improve the quality of cluster division.

Maintaining stable and orderly intelligent autonomous driving behavior in a closing scene is an important challenge. Compared with traditional chaos caused by an individual autonomous vehicle based on central control, when it breaks down, an intelligent cooperative autonomous driving group may effectively mitigate or alleviate the issue. There is no method to formulate an autonomous vehicle group and analyze its cooperative behavior by taking the aggregation, leading node change rate, and algorithm complexity of a vehicle group into account. This work formulates an aggregation degree-based Cooperative Model for Autonomous Vehicle Groups in a closing scene (CMAVG). First, we construct multi-roles and hierarchical autonomous vehicle groups. Then, we analyze their evolution behavior and present a dynamic evolution method based on it. Finally, we formulate CMAVG and give its solving method. We conduct extensive simulations in a simulated closing scene and a real one. Experimental results show that our autonomous vehicle group formation method outperforms a VANET clustering method and an autonomous vehicle group formation method in terms of aggregation degree, running time, and leading node change rate. CMAVG outperforms two cooperation methods for Internet of vehicles and an autonomous vehicle group cooperation method in terms of aggregation degree, leading node change rate, and vehicle group survival time.

Federated learning (FL) allows distributed devices to jointly train a global model while safeguarding the privacy of their local data. However, selecting and securing clients, especially in environments with potentially malicious participants, remains a critical challenge. This study proposes an innovative participant selection method to enhance both security and efficiency in centralized and decentralized FL frameworks. In the centralized framework, this method effectively excludes clients with weak privacy protections and optimization capabilities, thus increasing overall system security. For decentralized FL, a blockchain-supported approach is introduced, which further strengthens the robustness of the system. Using a dynamic role assignment algorithm, roles such as worker, validator, and miner are allocated based on security and performance metrics for each training round. The findings show that this method performs on a par with the scenarios free of malicious clients, demonstrating the value of blockchain technology in improving FL protocols. By addressing security vulnerabilities and improving training efficiency, this research contributes to the development of more secure and efficient FL systems, underscoring the importance of advanced participant selection and role assignment strategies.

According to Hughes phenomenon, the major challenges encountered in computations with learning models come from the scale of complexity, e.g. the so-called curse of dimensionality. Approaches for accelerated learning computations range from model- to implementation-level. The first type is rarely used in its basic form. Perhaps, this is due to the theoretical understanding of mathematical insights. We describe a model-level decomposition approach that combines both the decomposition of the objective function and of data. We perform a feasibility analysis of the resulting algorithm, both in terms of accuracy and scalability.

In recent years, some deep learning dehazing methods based on atmospheric scattering model mostly solve the dehazing results by using depth convolution neural networks (CNNs) to estimate the medium transmission map in the model. However, these methods usually ignored the potential correlation between the transmission map and the atmospheric light in the atmospheric scattering model, which can lead to colour distortion and incomplete dehazing in the dehazing results. To address this problem, this paper first presents a novel Haze-Veil model to increase the correlation between the model parameters by constructing an atmospheric veil term. Then, based on the proposed model, a haze-relevant end-to-end network (HRN) is designed to estimate the parameters of this model and directly output the final clear image. In addition, a cost function is designed by defining multi-object constraint cost functions to further establish the connections between the statistical attributes of the hazy image and the out of HRN. Experiments on benchmark images, which include synthesized and real images, show that HRN effectively removes haze and outperforms most of the existing and state-of-the-art dehazing methods.

A brain-computer interface (BCI) based on motor imagery (MI) enables users to communicate with the computer directly using brain signals. However, due to the low signal-to-noise ratio and significant inter-subject variations, its long calibration time hinders the development of brain-computer interfaces. Meta-learning, as the current popular framework in few-shot learning, enables the model to quickly adapt to new few-shot tasks by learning a series of similar tasks. In this paper, we propose a novel algorithm that combines pre-training and meta-learning. It can reduce the number of training samples required for the target subject and meanwhile ensure stable and reliable BCI performance. This is achieved by first learning general feature representations from a large number of other subjects' data through pre-training, and then further optimizing the model by task scale using meta-learning based on the pre-training stage. Applications to a dataset confirm the effectiveness of the combination of pre-training and meta-learning. Results indicate that the proposed algorithm outperforms the considered comparable baseline algorithm, early meta-learning frameworks without pre-training, and fine-tuning in transfer learning. In addition, experiments show that the selection of source subjects can further improve the overall performance of the algorithm, and the pre-training stage is crucial for the model to achieve good performance. This study has significant instruction for the application of BCI in the field of medical rehabilitation. It can improve the classification performance of the disabled with poor motor imagination characteristics by using the data of healthy typical subjects and greatly reducing their training time.

Existing deep-learning-based image steganalysis networks have problems such as large model sizes, significant runtime memory usage, and extensive computational operations, which hinder their deployment in many practical applications. To address these challenges, we applied model compression techniques to image steganalysis and designed a model called SASRNet, a slimming-assisted steganalysis residual network. We observed that the trainable scale factor of BN (batch normalization) layer in steganalysis network can be used as channel scaling factor for pruning. The channel-level sparsity of convolutional layers is enhanced by imposing L1 regularization on channel scaling factors and pruning less informative feature channels. With the goal of balancing performance and efficiency, the iterative algorithm is used to further compress the network to obtain a slimming- steganalysis detector. In contrast to many existing methods, our proposed method can be directly applied to steganalysis network architectures by introducing a minimal overhead to the training process. We have conducted extensive experiments on BOSSBase+BOWS2 dataset. Experiments show that, compared to the original steganalysis model, this method can achieve comparable performance with less than 5 % of the parameters, validating the feasibility and practicality of the new model.

In this paper, a PCA-SSA-DBIGRU-Attention multi-factor short-term power load forecasting model is proposed. Taking a complete account of the influence of meteorological factors, principal components analysis (PCA) is used to analyze the meteorological factors of daily minimum, maximum, daily average temperature, relative humidity, daily precipitation and power load data at the same time. The realization of original load data is dimensioned down. The complexity of power load forecasting models is reduced. Then, the Attention Double Bidirectional Gating Recurrent Unit (DBIGRU) model is constructed to calculate the different weights of the hidden layer states of the two-layer BIGRU. The hidden layer states are assigned different weights. The Sparrow Search Algorithm (SSA) is incorporated into the DBIGRU-Attention. The SSA-DBIGRU-Attention network model is constructed to optimize the learning rate, the number of iterations and the four hyperparameters of the first and second hidden layer neurons. The extracted principal components are input into SSA-DBIGRU-Attention to realize multi-factor short-term power load forecasting. Experimental results show that the prediction accuracy of the proposed model is improved, and the prediction time is reduced. Compared to the VMD-BILSTM, PCA-DBILSTM, CNN-GRU-Attention and CNN-BIGRU-Attention model, the four aspects of MAPE, MAE, RMSE and time are reduced by 29.55 %, 36.42 %, 32.34 % and 12.22 %, respectively, the R2 is improved by 3.09 %.