Distributed Denial of Service (DDoS) attacks continue to escalate in both frequency and sophistication, often overwhelming critical network infrastructures. While deep learning methods excel at recognizing malicious patterns, their lack of transparency undermines trust and hampers effective mitigation. This paper introduces a unified, on-premise pipeline that integrates an advanced flow based attack classifier with a local large language model (LLM) to deliver explainable, real-time DDoS defense. The proposed approach detects threats at the flow level, rapidly fags suspicious traffic, and then generates human-readable analyses and device specific countermeasures ranging from firewall rules to intrusion prevention system signatures all without transmitting data of-site. Through comprehensive testing on diverse, large scale network traces, we demonstrate that this framework not only achieves near-perfect detection accuracy but also considerably reduces operational costs and privacy risks associated with external cloud services. Furthermore, evaluators confirm the clarity and correctness of the automatically generated mitigation strategies, highlighting the system’s practicality in enterprise environments. Overall, our results validate on-premise, LLM-enhanced DDoS defense as a robust, transparent, and economical solution for safeguarding modern network ecosystems.

Since the release of the first warehouse management system (WMS), these systems have been systematically developed and improved to optimize warehouse operations, including inventory management, order fulfillment, receiving, picking, packing, and shipping. Among the many well-documented and well-known WMS systems, there are other systems with a similar level of maturity and comparable functionality, but not as popular, but still very appealing. Such a system is Pinquark, the flagship product of one of the leading Polish software vendors. In this sense, the aim of this article is to present its main features and discuss its further development. In particular, we introduce and outline the idea of reorienting warehouse management from a process-based to an activity-based approach. In this context, we discuss the preliminary results obtained through the study of contemporary literature, including methods addressing vehicle routing and product allocation problems.

The paper presents a survey-based study that aimed to determine the prevalence of anti-patterns in the Scrum software development methodology.A total of 35 anti-patterns were selected from the literature review, and 42 respondents working in software development organizations located in Poland indicated whether they had encountered each anti-pattern in their organizations.The study found that "Unfinished Tasks" was the most prevalent anti-pattern, highlighting the importance of proper planning and task management within sprints.Additionally, several other common anti-patterns were identified, including daily scrums being extended beyond the recommended time, user stories not being fully refined, and the sprint goal not being defined at the sprint planning meeting.The findings of this study provide valuable insights into the current state of Scrum methodology in software development organizations and highlight areas where there is room for improvement.

Cognitive bias is a phenomenon that has been extensively studied in stock trading and many other fields. This paper presents a framework for a Mobile Stock Trading Simulator (MSTS) that facilitates automatic investment in stocks with minimal human influence, by investigating the behavioral patterns and cognitive errors of stock market investors. The paper aims to determine whether investors’ investment strategies can be improved by detecting investment threats and reducing investment errors based on investors’ transaction histories. To accomplish this, we built a stock exchange simulator and implemented a decision tree to classify cognitive biases into one of six categories. By incorporating the behavioral patterns and cognitive biases of stock market investors into the MSTS's architecture, and by implementing a decision tree and stock exchange simulator, we can minimize the impact of human influence on automatic investments.

This study compares the results of two completely different models: statistical one (ARIMA) and deep learning one (LSTM) based on a chosen set of NASDAQ data. Both models are used to predict daily or monthly average prices of chosen companies listed on the NASDAQ stock exchange. Research shows which model performs better in terms of the chosen input data, parameters and number of features. The chosen models were compared using the relative metric mean square error (MSE) and mean absolute percentage error (MAPE). Selected metrics are typically used in regression problems. The performed analysis shows which model achieves better results by comparing the chosen metrics in different models. It is concluded that the ARIMA model performs better than the LSTM model in terms of using just one feature – historical price values – and predicting more than one time period, using the p, q parameters in the range from 0 to 2, Adam optimizer, tanh activation function, and 2xLSTM layer architecture. The longer the data window period, the better ARIMA performs, and the worse LSTM performs. The comparison of the models was made by comparing the values of the MAPE error. When predicting 30 days, ARIMA is about 3.4 times better than LSTM. When predicting an averaged 3 months, ARIMA is about 1.8 times better than LSTM. When predicting an averaged 9 months, ARIMA is about 2.1 times better than LSTM.

Affective computing (AfC) is a continuously growing multidisciplinary field, spanning areas from artificial intelligence, throughout engineering, psychology, education, cognitive science, to sociology. Therefore, many studies have been devoted to the aim of addressing numerous issues, regarding different facets of AfC solutions. However, there is a lack of classification of the AfC systems. This study aims to fill this gap by reviewing and evaluating the state-of-the-art studies in a qualitative manner. In this line of thinking, we put forward a threefold classification that breaks down to desktop and mobile AfC systems, and AfC machines. Moreover, we identified four types of AfC systems, based on the features extracted. In our opinion, the results of this study can serve as a guide for future affect-related research and design, on the one hand, and provide a better understanding on the role of emotions and affect in human-computer interaction, on the other hand.

Intelligent technologies are widely implemented in different areas of modern society but specific approaches should be applied in services. Basic relationships refer to supporting customers and people responsible for services offering for these customers. The aim of the paper is to analyze and evaluate the state-of-the art of artificial intelligence (AI) applications in the hospitality industry. Our findings show that the major deployments concern in-person customer services, chatbots and messaging tools, business intelligence tools powered by machine learning, and virtual reality & augmented reality. Moreover, we performed a survey (n = 178), asking respondents about their perceptions and attitudes toward AI, including its implementation within a hotel space. The paper attempts to discuss how the hotel industry can be motivated by potential customers to apply selected AI solutions. In our opinion, these results provide useful insights for understanding the phenomenon under investigation. Nevertheless, since the results are not conclusive, more research is still needed on this topic. Future studies may concern both qualitative and quantitative methods, devoted to developing models that: a) quantify the potential benefits and risks of AI implementations, b) determine and evaluate the factors affecting the AI adoption by the customers, and c) measure the user (guest) experience of the hotel services, fueled by AI-based technologies.

Among many global challenges, climate change is one of the biggest challenges of our times. While it is one of the most devastating problems humanity has ever faced, one question naturally arises: can individuals make a difference? We believe that everyone can contribute and make a difference to the community and lives of others. However, there is still a lack of effective strategies to promote and facilitate pro-environmental behavior of individuals. To fill this gap, in this paper, we introduce and discuss the Greencoin mobile application prototype. The app is built on existing intelligent data-driven technologies, including supervised and unsupervised learning techniques. Since its end-users will mostly concern the city dwellers, the project falls into the scope of the ongoing research in the area of smart city applications. Nevertheless, the application is still in the design phase, we believe it is a good starting point to spark discussion on its further directions of development, as well as to draw the attention of both national and international audiences to the issues raised.

The variety of hardware devices and the diversity of their users imposes new requirements and expectations on designers and developers of mobile applications (apps).While the Internet has enabled new forms of communication platform, online stores provide the ability to review apps.These informal online app reviews have become a viral form of electronic wordof-mouth (eWOM), covering a plethora of issues.In our study, we set ourselves the goal of investigating whether online reviews reveal usability and user experience (UUX) issues, being important quality-in-use characteristics.To address this problem, we used sentiment analysis techniques, with the aim of extracting relevant keywords from eWOM WhatsApp data.Based on the extracted keywords, we next identified the original users' reviews, and individually assigned each attribute and dimension to them.Eventually, the reported issues were thematically synthesized into 7 attributes and 8 dimensions.If one asks whether online reviews reveal genuine UUX issues, in this case, the answer is definitely affirmative.

Communication by electronic mail (e-mail), once extravagant, is now the usual way to exchange data and information.Widely accepted by Internet users, business and governments, it is claimed to be the key part of the e-revolution.E-mail systems have been successfully implemented in almost all computer-aided domains of human interest, providing efficient, effective and permanent mechanisms of transmission.However, to date, the capability to exhibit an ordered list (sequence) of e-mail message senders and recipients, with the respective duration time between receiving and answering is still lacking.To fill this gap, in this paper we introduce the SOMF algorithm for mining such sequences from server log data.We specified a three-stage approach to comprehensively target the problem.The first stage concerns a data preparation task in order to assemble the input for the algorithm.The second, known as data mining, is the automatic analysis of data input performed in an unsupervised model by the SOMF algorithm.The third embraces output (knowledge) visualization, interpretation and evaluation.The given case study is based on the log data from an operational STMP server.By design, this simplified example brings about a better understanding of the solution, indicating one of its potential applications to identify and eliminate deadlocks in the realization of business processes.We also tested the efficiency of the implementation of the algorithm in five independent experiments on seven datasets, ranging in size.The results show that mining even 1 million rows is performed in approximately less than 6 minutes.

Software usability plays a major role in the quality perceived by its users.However, a variety of definitions and associated attributes shows that there is still no consensus in this area.The overall purpose of this paper is to present the results of a critical and rigorous literature review, the aim of which is to demonstrate all the relevant usability definitions and related attributes introduced till now.This comprehensive view, depicted by a time-framed knowledge map, provides an indepth understanding of the observed evolution on the one hand, and also serves as a guide for usability engineers to address some non-functional requirements, on the other.

On the surface, one might think that revealing the factors that impact on software product usability and the success of an entire project would be relatively simple; however, reported evidence from practitioners and scholars frequently shows the opposite. The aim of this study was to determine factors with a positive (negative) impact on delivering usability in a software product and the success (failure) of an entire project. This paper presents the results of our study, where 11 factors were identified and described, along with an outline of 11 goal-oriented rules incorporating the expertise and knowledge of project managers. The elaborated body of knowledge, positively evaluated by IT professionals, would seem to be a valuable asset during the risk analysis performed before the kick-off of a project as well as in understanding the notion of usability.

Considering different aspects of knowledge functioning, context is poorly understood in spite of intuitively identifying this concept with environmental recognition.For dynamic knowledge, context especially seems to be an essential factor of change.Investigation on the impact of context on knowledge dynamics or more generally on the relationship between knowledge and its contextual interpretation is important in order to understand knowledge dynamics.The aim of this paper is to research and examine the nature of knowledge transformation (a specific sort of life-cycle), and to identify contextual factors affecting knowledge dynamics.

Knowledge is seen as one of the main resources for organizations providing knowledge-intensive services.Therefore, sharing and reusing are the main goals of the modern knowledge management (KM) approach, driven by information and communication technologies (ICT).However, one must ask for the details in order to provide the means and tools to design and deploy an environment able to fulfil these two goals.We observed that the interactions occurring on knowledge resources can be reduced to a directional flow, and further described by distinguished internal phases.In our research we put forward two research questions: (1) what are the main entities in the knowledge flow supported by ICT? and (2) what are the main phases of the knowledge flow?In this paper we introduce the generic lemniscate knowledge flow model, which, grounded on recognized theory, learned principles and gathered practices, provides foundations to solve the above problem.

Effective project management requires the development of a realistic plan which aims to ensure the success of the project and ultimately deliver a high quality product to customers.However, experience shows that the majority of software vendors managing projects suffer from numerous problems to provide usability in IT solutions and complete a project in a given time with success.In this paper we discuss, analyze and synthesize the outcomes of a study conducted among IT firms in Poland.As a result, we have identified eight stimulants and three non-stimulants that affect the usability of software products, which later were stratified into three levels.Finally, we outline some of the lessons learned, summarized and expressed as a set of eleven goal-oriented rules.

In this paper we present the results of a study that aims to evaluate the usability of three selected web services, based on eye-tracking and thinking aloud techniques.The gathered comments and observations, recapitulated and supported by particular measures, allow us to discover and describe typical user behavior pertaining to given tasks to solve.