Abstract
Strategic term re-writing and attribute grammars are two powerful programming techniques widely used in language engineering. The former relies on strategies to apply term re-write rules in defining large-scale language transformations, while the latter is suitable to express context-dependent language processing algorithms. These two techniques can be expressed and combined via a powerful navigation abstraction: generic zippers. This results in a concise zipper-based embedding offering the expressiveness of both techniques. Such elegant embedding has a severe limitation since it recomputes attribute values. This paper presents a proper and efficient embedding of both techniques. First, attribute values are memoized in the zipper data structure, thus avoiding their re-computation. Moreover, strategic zipper based functions are adapted to access such memoized values. We have implemented our memoized embedding as the Ztrategic library and we benchmarked it against the state-of-the-art Strafunski and Kiama libraries. Our first results show that we are competitive against those two well established libraries.

Abstract
Digital Marketing sets a sequence of strategies responsible for maximizing the interaction between companies and their target audience. One of them, known as Customer Success, establishes long-term techniques capable of projecting the sustainable value of a given customer to a company, monitoring the indexers that translate its activities. Therefore, this paper intends to address the need to develop an innovative tool that allows the creation of a temporal knowledge base composed of the behavioral evolution of customers. The CRISP-DM model benefits the processing and modeling of data capable of generating knowledge through the application and combination of the results obtained by machine learning algorithms specialized in time series. Time Series K-Means allows the clustering and differentiation of consumers characterized by their similar habits. Through the formulation of profiles, it is possible to apply forecasting methods that predict the following trends. The proposed solution provides the understanding of time series that profile the flow of customer activity and the use of the evidenced dynamics for the future prediction of these behaviors. © MIR Labs, www.mirlabs.net/ijcisim/index.html

Abstract
Water bodies are complex and interconnected systems that play a crucial role in both our environment and our economy. Studying these water bodies is therefore essential but collecting and analyzing water samples can be challenging, particularly when dealing with large volumes of water. This article presents a system capable of autonomously filtering large volumes of water through standard marine biology filters and preserving them to later be analyzed. The system's preliminary results are presented in this paper.

Abstract
As the demand for electric charging accelerates, so does the stress on the relatively insufficient public charging infrastructure. To appropriately manage and scale charging infrastructure, there is a need for support tools capable of predicting the utilization and sales of charging stations, as well as the traffic flow of users from their original location to the charging stations. Therefore, this article proposes a generic methodology for infrastructure placement, namely forecasting demand and predicting its flow to the supply points. The methodology is applied in a case study to the electric charging grid of Portugal with real data, in the context of the needs of a particular charging point operator (CPO). Demand is first forecasted at a high-granularity level with a demand disaggregation model, followed by its capture by the grid of chargers using a parameterized gravity model. Validation is performed by comparing actual with predicted sales per charging station. Adequate visualizations to support decision-making are presented.

Abstract
With the ever-growing complexity of deep learning models for face recognition, it becomes hard to deploy these systems in real life. Researchers have two options: 1) use smaller models; 2) compress their current models. Since the usage of smaller models might lead to concerning biases, compression gains relevance. However, compressing might be also responsible for an increase in the bias of the final model. We investigate the overall performance, the performance on each ethnicity subgroup and the racial bias of a State-of-the-Art quantization approach when used with synthetic and real data. This analysis provides a few more details on potential benefits of performing quantization with synthetic data, for instance, the reduction of biases on the majority of test scenarios. We tested five distinct architectures and three different training datasets. The models were evaluated on a fourth dataset which was collected to infer and compare the performance of face recognition models on different ethnicity.

Abstract
Event extraction is an Information Retrieval task that commonly consists of identifying the central word for the event (trigger) and the event's arguments. This task has been extensively studied for English but lags behind for Portuguese, partly due to the lack of task-specific annotated corpora. This paper proposes a framework in which two separated BERT-based models were fine-tuned to identify and classify events in Portuguese documents. We decompose this task into two sub-tasks. Firstly, we use a token classification model to detect event triggers. To extract event arguments, we train a Question Answering model that queries the triggers about their corresponding event argument roles. Given the lack of event annotated corpora in Portuguese, we translated the original version of the ACE-2005 dataset (a reference in the field) into Portuguese, producing a new corpus for Portuguese event extraction. To accomplish this, we developed an automatic translation pipeline. Our framework obtains F1 marks of 64.4 for trigger classification and 46.7 for argument classification setting, thus a new state of the art reference for these tasks in Portuguese.