Federated learning is a multiple device collaboration setup designed to solve machine learning problems under framework for aggregation and knowledge transfer in distributed local data. This distributed model ensures the privacy of data at each local node. Owing to its relevance, there has been extensive research activities and outcomes in federated learning with expanded applicability to different areas by the research community. As such, there is a vast research archive made available by the community with research work and articles related to the various aspects of federated learning such as applications, challenges, privacy, functionalities, and design. With respect to the function and design of federated learning, client selection, aggregation, knowledge transfer, management of distributed data (Non-IID), Incentive of data and communication cost are of paramount importance. Any effective design of federated learning requires these aspects to be well considered. There are numerous survey articles found among the available literature that focus on its application and challenges, opportunities, data privacy and protection, as well as on federated learning on internet of things, federated learning on edge computing, etc. In this paper, a review of the available literature on the various elements of design and functionalities in federated learning has been carried out with an aim to lay emphasis on the important challenges and research opportunities. More specifically, this work has endeavored to understand and summarize the various functional methods available, along with their techniques and goals. Additionally, it has strived to get a bird’s eye view of how various functions and designs of federated learning have been used in applications, and how it has helped uncover challenges and promising research directions for the future.

Smart city applications that request sensitive user information necessitate a comprehensive data privacy solution. Federated learning (FL), also known as privacy by design, is a new paradigm in machine learning (ML). However, FL models are susceptible to adversarial attacks, similar to other AI models. In this paper, we propose federated adversarial training (FAT) strategies to generate robust global models that are resistant to adversarial attacks. We apply two adversarial attack methods, projected gradient descent (PGD) and the fast gradient sign method (FGSM), to our air pollution dataset to generate adversarial samples. We then evaluate the effectiveness of our FAT strategies in defending against these attacks. Our experiments show that FGSM-based adversarial attacks have a negligible impact on the accuracy of global models, while PGD-based attacks are more effective. However, we also show that our FAT strategies can make global models robust enough to withstand even PGD-based attacks. For example, the accuracy of our FAT-PGD and FL-mixed-PGD models is 81.13% and 82.60%, respectively, compared to 91.34% for the baseline FL model. This represents a reduction in accuracy of 10%, but this could be potentially mitigated by using a more complex and larger model. Our results demonstrate that FAT can enhance the security and privacy of sustainable smart city applications. We also show that it is possible to train robust global models from modest datasets per client, which challenges the conventional wisdom that adversarial training requires massive datasets.

In accordance with the Sustainable Development Goals, the exponential expansion of machine learning (ML) and artificial intelligence (AI) presents an excellent chance to build more effective tools and solutions and generate positive social impact. According to the WHO report, global PM pollution causes more than 8 million deaths annually. This is the fundamental reason we are performing this research. This research proposes estimating air quality using deep learning. The proposed model can surpass the state-of-the-art model in terms of RMSE, R-squared, and accuracy, which have respective values of 30.10, 0.83, and 76.92%. In order to explain the model’s output, LIME has been implemented. According to LIME’s explanation, the proposed model’s output is trustworthy. Because it reveals that the sky, and not other places such as buildings, was the source of the most impactful superpixels on the model’s decision. We hope that with this discovery, we can contribute to the theme of “AI for social good,” notably in the domains of the environment and human welfare.

Deep learning and additive manufacturing have progressed together in the previous couple of decades. Despite being one of the most promising technologies, they have several flaws that a collaborative effort may address. However, digital manufacturing has established itself in the current industrial revolution and it has slowed down quality control and inspection due to the different defects linked with it. Industry 4.0, the most recent industrial revolution, emphasizes the integration of intelligent production systems and current information technologies. As a result, deep learning has received a lot of attention and has been shown to be quite effective at understanding image data. This review aims to provide a cutting-edge deep learning application of the AM approach and application. This article also addresses the current issues of data privacy and security and potential solutions to provide a more significant dimension to future studies.

Research into the detection, classification, and prediction of internal defects using surface morphology data of parts created via powder bed fusion-type additive manufacturing has become a hot topic in the previous decade thanks to the development of deep learning. However, there is no other evidence to evaluate the model other than accuracy and metrics. In this paper, a novel data set is compiled from various literature and other sources to evaluate the black box model using explainable artificial intelligence (XAI). The data set contains three major powder bed fusion defects: gas porosity, lack of fusion, and balling. The anomaly was initially found using convolutional neural networks (CNN) and transfer learning. Based on test data, a model comparison was performed to determine the best accuracy and an F1 score. VGG16 has outperformed all other models in terms of accuracy, with an F1 score of 98.6 percent. Further, the model has been compared with the existing state-of-the-art model for classification in the domain of powder bed fusion defects. Finally, VGG16 was employed to interpret and explain the test data set. The LIME explanations revealed that the feature predicted by the model was present in conjunction with the fault. As a result, we are confident that the proposed model with XAI would considerably improve the fairness and trustworthiness of the output result in the powder bed fusion field. This can also aid in the automation of additive manufacturing in the realm of Industry 4.0.