Researchers from leading technology companies, prestigious universities worldwide, and the open-source community have made substantial strides in the field of facial recognition studies in recent years. Experiments indicate that facial recognition approaches have not only achieved but surpassed human-level accuracy. A contemporary facial recognition process comprises four key stages: detection, alignment, representation, and verification. Presently, the focus of facial recognition research predominantly centers on the representation stage within the pipelines. This study conducted experiments exploring alternative combinations of nine state-of-the-art facial recognition models, six cutting-edge face detectors, three distance metrics, and two alignment modes. The co-usability performances of implementing and adapting these modules were assessed to precisely gauge the impact of each module on the pipeline. Theoretical and practical findings from the study aim to provide optimal configuration sets for facial recognition pipelines.

To explore the opinions and the level of awareness of university students on renewable energy and environment issues in the fields of engineering and economics/business in Canada, Romania, and Turkey, surveys were conducted in several universities in these three countries. The survey results that are presented and discussed here indicate that while there are differences between the three groups, they are small and can be explained by cultural and socioeconomic factors. A larger study with an expanded survey questionnaire applied to a wider spectrum of groups in a larger set of countries would be useful to identify differences and educational needs.

Various human activities emit greenhouse gasses (GHGs) that contribute to global climate change. These include the burning of fossil fuels for energy production, transportation, and industrial uses, and the clearing of forests to create farmland and pasture, all for urban and industrial development. As a result, temperatures around the world are rising, extreme weather events are occurring more frequently, and human health is suffering because of these changes. As a result of massive traffic, agriculture, and urbanization, the natural environment is being destroyed, negatively affecting humans and other living things. Humanity plans to live in smart cities within this ecosystem as the world evolves around these mutations. A smart city uses technology and data to improve the quality of life of its citizens and the efficiency of its urban systems. Smart cities have the potential to be more sustainable because they use technology and data to improve the efficiency of urban systems and reduce the negative impact of human activities on the environment. Smart cities can also use technology to improve green transportation and waste management and reduce water consumption, which can help conserve natural resources and protect the environment. Smart cities can create livable, efficient, and sustainable urban environments using technology and data. This paper presents a new Enterprise Architecture Framework for reducing carbon emissions for environmental sustainability that combines gamification and green behavior with blockchain architecture to ensure a system that is trustworthy, secure, and scalable for shareholders, citizens, service providers, and technology vendors. In order to achieve this, the hyper-integrated framework approach explains a roadmap for how sustainability for reducing carbon emissions from transportation is based on an optimized MaaS approach improved by gamification. As part of this study, a computational model and a formulation are proposed to calculate the activity exchange values in the MaaS ecosystem for swapping, changing, and bartering for assets within the integrated system. This paper aims to propose the framework and a module interoperability approach, so numerical values for computation parameters are not included as they may belong to other research studies. In spite of this, a case study section has been provided as an example of a calculation approach.

Facial recognition research has achieved significant progress in recent years. State-of-the-art facial recognition models have already passed the level of human accuracy. In the meantime, facial recognition is already used in many fields, including making purchases, authenticating mobile applications, verifying identities in online shopping, and automating border control in airports. This paper compares different database options based on different tasks and use cases of facial recognition applications from the perspective of scalability. In particular, a novel approach to graph databases is proposed to detect false positive misclassifications in facial recognition. Furthermore, the latest homomorphic encryption schemes enable cloud-based facial recognition to run with encrypted data without requiring private keys. In addition to providing a guide for researchers and studies on facial recognition systems, the purpose of this article is also to create a perspective for the use of the most appropriate system.

Facial recognition technology has seen significant advancements, impacting security, surveillance, and personal identification. Deep neural networks have enhanced accuracy and reliability, with integration into everyday devices further accelerating adoption. Researchers explore combining Deep Neural Networks with Gradient Boosting Machines for improved performance. This paper proposes Boosted LightFace, a hybrid Deep Neural Networks and Gradient Boosting Machines model leveraging robust facial recognition and face detection models. The architecture first integrates predictions from five high-performing DNN models. Their distance metrics and classification outcomes are engineered into a tabular dataset of 6,000 image pairs with 13 features. This dataset is then trained using a highly efficient LightGBM model with a low learning rate of 0.01 and 1000 estimators, incorporating an early stopping mechanism, and employing 10-fold cross-validation to maximize generalization. Recent research identifies FaceNet512d as a robust model, surpassing human recognition on the Labeled Faces in The Wild dataset with 98.4% score. Boosted LightFace achieves 99.1% accuracy, surpassing human recognition by 1.6% and outperforming the best single model in LightFace by 0.7%, underscoring the potential of integrating Deep Neural Networks and Gradient Boosting Machines models in advancing facial recognition technology. Furthermore, Boosted LightFace not only outperforms individual models in terms of accuracy but also surpasses them in precision, recall, F1, and AUC scores, highlighting its comprehensive superiority.

Facial recognition systems rely on embeddings to represent facial images and determine identity by verifying if the distance between embeddings is below a pre-tuned threshold. While embeddings are not reversible to original images, they still contain sensitive information, making their security critical. Traditional encryption methods like AES are limited in securely utilizing cloud computational power for distance calculations. Homomorphic Encryption, allowing calculations on encrypted data, offers a robust alternative. This paper introduces CipherFace, a homomorphic encryption-driven framework for secure cloud-based facial recognition, which we have open-sourced at http://github.com/serengil/cipherface. By leveraging FHE, CipherFace ensures the privacy of embeddings while utilizing the cloud for efficient distance computation. Furthermore, we propose a novel encrypted distance computation method for both Euclidean and Cosine distances, addressing key challenges in performing secure similarity calculations on encrypted data. We also conducted experiments with different facial recognition models, various embedding sizes, and cryptosystem configurations, demonstrating the scalability and effectiveness of CipherFace in real-world applications.