Abstract
We introduce a novel method for movie genre classification, capitalizing on a diverse set of readily accessible pretrained models. These models extract high-level features related to visual scenery, objects, characters, text, speech, music, and audio effects. To intelligently fuse these pretrained features, we train small classifier models with low time and memory requirements. Employing the transformer model, our approach utilizes all video and audio frames of movie trailers without performing any temporal pooling, efficiently exploiting the correspondence between all elements, as opposed to the fixed and low number of frames typically used by traditional methods. Our approach fuses features originating from different tasks and modalities, with different dimensionalities, different temporal lengths, and complex dependencies as opposed to current approaches. Our method outperforms state-of-the-art movie genre classification models in terms of precision, recall, and mean average precision (mAP). To foster future research, we make the pretrained features for the entire MovieNet dataset, along with our genre classification code and the trained models, publicly available.

Abstract
Secure multiparty computation (SMC) provides collaboration among multiple parties, ensuring the confidentiality of their private information. However, classical SMC implementations encounter significant security and efficiency challenges. Resorting to the entangled Greenberger-Horne-Zeilinger (GHZ) state, we propose a quantum-based two-party protocol to compute binary Boolean functions, with the help of a third party. We exploit a technique in which a random Z-phase rotation on the GHZ state is performed to achieve higher security. The security and complexity analyses demonstrate the feasibility and improved security of our scheme compared to other SMC Boolean function computation methods. Additionally, we implemented the proposed protocol on the IBM QisKit and found consistent outcomes that validate the protocol's correctness.

Abstract
Turbidity and suspended sediment concentration are crucial parameters indicative of water quality, playing pivotal roles in evaluating the well-being of aquatic ecosystems and the effectiveness of water treatment processes. This manuscript provides an in-depth review of various methods and instruments in use for in situ and inline applications. The exploration of optical instrumentation is central to this review, examining its widespread use and current challenges within standard methods, commercial instruments and scientific research. The study also delves into alternative techniques, such as acoustic and capacitive methods, elucidating their applications, calibration intricacies, and practical considerations. Furthermore, the paper scrutinizes the emerging importance of satellite and aerial imaging processing as a supplementary tool for turbidity monitoring, underscoring its potential to offer comprehensive insights on a larger scale. The review emphasizes the key accomplishments and challenges of the state-of-the-art technologies, providing a comprehensive overview of the current stage of the field and its prospects. and aims to provide valuable insights for researchers, practitioners, and decision-makers involved in environmental monitoring and water facility management, enabling a deeper comprehension of the significance of turbidity and suspended sediment concentration in safeguarding water quality and ecosystem health.

Abstract
Frequency Containment Reserve (FCR) Cooperation is a European effort to integrate several countries in an integrated international electricity market platform for FCR procurement. In this market, Balancing Service Providers (BSPs) are on the supply side and Transmission System Operators (TSOs) on the demand side. This paper proposes a novel settlement scheme for sharing costs among TSOs; it proposes no changes to existing market clearing rules or to the existing settlement of the BSPs' revenues. It is shown that the current TSO settlement scheme is an inequitable mechanism that originates negative costs for some TSOs in specific conditions, which are extensively discussed. The proposed TSO settlement scheme overcomes these inequities. In the proposed scheme, TSOs begin paying the local BSPs for the cleared bids needed locally, and the remaining imports are calculated in a subsequent step. Doing so avoids using the so-called import/export costs, which are demonstrated to be the source of the inequities in the current scheme. It is shown that if the proposed pricing scheme had been adopted from July 2019 to December 2022, all TSOs would have been affected. Specifically, the most negatively impacted TSO would have its accumulated costs increased by 16% and the most positively impacted TSO would have its accumulated cost decreased by 32%. The inequities of the current mechanism amount to more than 50 Me or 7.4% of the total accumulated costs. Although the proposed mechanism is tested here under the FCR Cooperation, it can be applied to other markets where the rules allow different local settlement prices.

Abstract
Hydrogen is currently getting more and more attention in the European climate strategy as a promising enabling technology to decarbonize industry, transport sector and to provide a long-term, high-capacity energy storage solution. However, to truly contribute to the reduction of CO2 emissions, hydrogen must be produced respecting a principle of additionality, to ensure that it is produced using renewable energy sources and that its production does not decrease the green energy supplied to other loads. This study tracks the share of renewables generation in the energy mix used to produce hydrogen by applying a power flow tracing technique integrated with an optimal power flow analysis. This method allows the minimization of the system operation costs, while maximizing the green hydrogen production and considering the additionality principle. The system cost function is also modified to include the sizing and allocation of conventional batteries in the grid, and assess their ability to further increase the share of green energy in hydrogen production.

Abstract
Facial expression is a way of communication that can be used to interact with computers or other electronic devices and the recognition of emotion from faces is an emerging practice with applications in many fields. Many cloud-based vision application programming interfaces are available that recognize emotion from facial images and video. In this article, the performances of two well-known APIs were compared using a public dataset of 980 images of facial emotions. For these experiments, a client program was developed that iterates over the image set, calls the cloud services, and caches the results of the emotion detection for each image. The performance was evaluated in each class of emotions using prediction accuracy. It has been found that the prediction accuracy for each emotion varies according to the cloud service being used. Similarly, each service provider presents a strong variation of performance according to the class being analyzed, as can be seen in more detail in these articles.