Abstract
Network security encloses a wide set of technologies dealing with intrusions detection. Despite the massive adoption of signature-based network intrusion detection systems (IDSs), they fail in detecting zero-day attacks and previously unseen vulnerabilities exploits. Behaviour-based network IDSs have been seen as a way to overcome signature-based IDS flaws, namely through the implementation of machine-learning-based methods, to tolerate new forms of normal network behaviour, and to identify yet unknown malicious activities. A wide set of machine learning methods has been applied to implement behaviour-based IDSs with promising results on detecting new forms of intrusions and attacks. Innovative machine learning techniques have emerged, namely deep-learning-based techniques, to process unstructured data, speed up the classification process, and improve the overall performance obtained by behaviour-based network intrusion detection systems. The use of realistic datasets of normal and malicious networking activities is crucial to benchmark machine learning models, as they should represent real-world networking scenarios and be based on realistic computers network activity. This paper aims to evaluate CSE-CIC-IDS2018 dataset and benchmark a set of deep-learning-based methods, namely convolutional neural networks (CNN) and long short-term memory (LSTM). Autoencoder and principal component analysis (PCA) methods were also applied to evaluate features reduction in the original dataset and its implications in the overall detection performance. The results revealed the appropriateness of using the CSE-CIC-IDS2018 dataset to benchmark supervised deep learning models. It was also possible to evaluate the robustness of using CNN and LSTM methods to detect unseen normal activity and variations of previously trained attacks. The results reveal that feature reduction methods decreased the processing time without loss of accuracy in the overall detection performance.

Abstract
The subjectiveness of multimedia content description has a strong negative impact on tag-based information retrieval. In our work, we propose enhancing available descriptions by adding semantically related tags. To cope with this objective, we use a word embedding technique based on the Word2Vec neural network parameterized and trained using a new dataset built from online newspapers. A large number of news stories was scraped and pre-processed to build a new dataset. Our target language is Portuguese, one of the most spoken languages worldwide. The results achieved significantly outperform similar existing solutions developed in the scope of different languages, including Portuguese. Contributions include also an online application and API available for external use. Although the presented work has been designed to enhance multimedia content annotation, it can be used in several other application areas.

Abstract
Background: Internet-based interventions can be effective in the treatment of depression. However, internet-based interventions for older adults with depression are scarce, and little is known about their feasibility and effectiveness. Objective: To present the design of 2 studies aiming to assess the feasibility of internet-based cognitive behavioral treatment for older adults with depression. We will assess the feasibility of an online, guided version of the Moodbuster platform among depressed older adults from the general population as well as the feasibility of a blended format (combining integrated face-to-face sessions and internet-based modules) in a specialized mental health care outpatient clinic. Methods: A single-group, pretest-posttest design will be applied in both settings. The primary outcome of the studies will be feasibility in terms of (1) acceptance and satisfaction (measured with the Client Satisfaction Questionnaire-8), (2) usability (measured with the System Usability Scale), and (3) engagement (measured with the Twente Engagement with eHealth Technologies Scale). Secondary outcomes include (1) the severity of depressive symptoms (measured with the 8-item Patient Health Questionnaire depression scale), (2) participant and therapist experience with the digital technology (measured with qualitative interviews), (3) the working alliance between patients and practitioners (from both perspectives; measured with the Working Alliance Inventory-Short Revised questionnaire), (4) the technical alliance between patients and the platform (measured with the Working Alliance Inventory for Online Interventions-Short Form questionnaire), and (5) uptake, in terms of attempted and completed modules. A total of 30 older adults with mild to moderate depressive symptoms (Geriatric Depression Scale 15 score between 5 and 11) will be recruited from the general population. A total of 15 older adults with moderate to severe depressive symptoms (Geriatric Depression Scale 15 score between 8 and 15) will be recruited from a specialized mental health care outpatient clinic. A mixed methods approach combining quantitative and qualitative analyses will be adopted. Both the primary and secondary outcomes will be further explored with individual semistructured interviews and synthesized descriptively. Descriptive statistics (reported as means and SDs) will be used to examine the primary and secondary outcome measures. Within-group depression severity will be analyzed using a 2-tailed, paired-sample t test to investigate differences between time points. The interviews will be recorded and analyzed using thematic analysis. Results: The studies were funded in October 2019. Recruitment started in September 2022. Conclusions: The results of these pilot studies will show whether this platform is feasible for use by the older adult population in a blended, guided format in the 2 settings and will represent the first exploration of the size of the effect of Moodbuster in terms of decreased depressive symptoms. © 2022 Khadicha Amarti, Mieke H J Schulte, Annet Kleiboer.

Abstract
Modern organizations face numerous physical security threats, from fire hazards to more intricate concerns regarding surveillance and unauthorized personnel. Conventional standalone fire and intrusion detection solutions must be installed and maintained independently, which leads to high capital and operational costs. Nonetheless, due to recent developments in smart sensors, computer vision techniques, and wireless communication technologies, these solutions can be integrated in a modular and low-cost manner. This work introduces Integrated Physical Security System (IP2S), a multi-agent system capable of coordinating diverse Internet of Things (IoT) sensors and actuators for an efficient mitigation of multiple physical security events. The proposed system was tested in a live case study that combined fire and intrusion detection in an industrial shop floor environment with four different sectors, two surveillance cameras, and a firefighting robot. The experimental results demonstrate that the integration of several events in a single automated system can be advantageous for the security of smart buildings, reducing false alarms and delays.

Abstract
Purpose There is a scarcity of empirical evidence in the literature on the chain of causality involving tax incentives for Research and Development (R&D) activities and their subsequent transformation into innovation. This study aims to assess the influence of R&D tax incentives on the organizational attributes of Portuguese firms to identify how they are converted into innovation. Design/methodology/approach A structural research model consisting of 339 companies that benefited from the Fiscal Incentive System supporting R&D in Enterprises, during the period from 2013 to 2016, was developed. This was done to assess the role of R&D tax incentives on the organizational attributes that form the innovation capacity. The model was validated using the multivariate statistical technique of structural equation modeling with partial least squares estimation (partial least squares structural equation modeling - PLS-SEM). Findings The results found suggest that although it is not possible to unequivocally identify the mechanisms used to convert tax incentives into innovation, it is possible to conclude that they play an important spillover effect for the construction and strengthening of organizational attributes. These form the basis of innovation capacity, to the extent that they positively influence the firms' total assets, equity, liabilities, number of employees and sales. Hence, contributions are brought to both the literature on tax incentives and the general literature on innovation. Originality/value For policymakers, the evidence points to the fact that in addition to the incentives provided, novel mechanisms need to be established to help firms develop their absorptive capacity. The objective is to effectively convert the incentives received into innovation through the organizational attributes analyzed. From the firms' point of view, the results found suggest that tax incentives act as a catalyst for making R&D investments. Additionally, there is an influence on employability, which effectively enhances the chances of innovation in the long run. Tax incentives received by Portuguese firms also have the effect of promoting economic dynamism - by enhancing the following: investments in infrastructure, the hiring of employees and the increasing of sales, generating positive externalities for both firms and society.

Abstract
Time expressions embedded in text are important for many downstream tasks in NLP and IR. They have been, for example, utilized for timeline summarization, named entity recognition, temporal information retrieval, question answering and others. In this paper, we introduce a novel analytical approach to analyzing characteristics of time expressions in diachronic text collections. Based on a collection of news articles published over a 33-years' long time span, we investigate several aspects of time expressions with a focus on their interplay with publication dates of containing documents. We utilize a graph-based representation of temporal expressions to represent them through their co-occurring named entities. The proposed approach results in several observations that could be utilized in automatic systems that rely on processing temporal signals embedded in text. It could be also of importance for professionals (e.g., historians) who wish to understand fluctuations in collective memories and collective expectations based on large-scale, diachronic document collections.